CN107622443A - Data processing method, data processing equipment and computer-readable recording medium - Google Patents
Data processing method, data processing equipment and computer-readable recording medium Download PDFInfo
- Publication number
- CN107622443A CN107622443A CN201710701240.8A CN201710701240A CN107622443A CN 107622443 A CN107622443 A CN 107622443A CN 201710701240 A CN201710701240 A CN 201710701240A CN 107622443 A CN107622443 A CN 107622443A
- Authority
- CN
- China
- Prior art keywords
- user
- behavior
- network behavior
- characteristic
- network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Abstract
Data processing method, data processing equipment and computer-readable recording medium.The invention discloses a kind of data processing method for being used to identify net loan behavior, comprise the following steps:Gather the Internet data of default user network behavior;The characteristic of default user network behavior is obtained according to the Internet data of the default user network behavior collected;According to the characteristic of the default user network behavior, judging user, whether there occurs net loan behavior.The technique effect that the net loan behavior to user is identified and monitored can be realized on the data processing equipments such as computer, mobile phone terminal by having reached.The present invention also provides a kind of data processing equipment and computer-readable recording medium.
Description
Technical field
The present invention relates to technical field of the computer network, more particularly to a kind of data processing method based on network behavior,
Data processing equipment and computer-readable recording medium.
Background technology
With the development of Internet technology, internet is had been applied in all trades and professions, for example, internet finance is in recent years
To have become one of focus of each commercial finance institution market competition.Wherein, it is exactly to interconnect that P2P (Peer-to-Peer) net, which is borrowed,
A big product of finance is netted, is a kind of to borrow the microfinance debt-credit that gathers together to a kind of small amount among the people for having credit requirement crowd
Loan pattern.
But P2P net borrow access threshold is low and the deficiency of supervision due to, often have occur insolvency borrow
After the borrower of money carries out net loan, such as the crowd such as college student, because the student suicide event of insolvency loan is sent out again and again
It is raw.
Existing technology can not realize that borrowing behavior to the net of user is identified and monitors, such as guardian or student
Father and mother can not know borrowed using whether the people of the consumption electronic products such as computer, tablet personal computer, mobile phone terminal nets in P2P on platform
There occurs net loan behavior, it is impossible to prevents enter with preventing such borrower for not possessing loan qualification or insolvency loan in time
Row net is borrowed;There is provided the mechanism of net loan platform or third-party monitoring person can not in time prevent and not possess loan qualification with preventing such
Or the borrower of insolvency loan carries out net loan.
The content of the invention
It is a primary object of the present invention to provide a kind of data that the net loan behavior of user can be identified and be monitored
Processing method, data processing equipment and computer-readable recording medium.
To achieve the above object, a kind of data processing method for being used to identify net loan behavior provided by the invention, including with
Lower step:
The Internet data of default user network behavior is gathered, the default user network behavior includes user and accesses letter
The network behavior of website is borrowed, and user accesses Web bank or network payment net after credit website is accessed in preset time
The network behavior stood;
The feature of default user network behavior is obtained according to the Internet data of the default user network behavior collected
Data, the characteristic of the default user network behavior include the characteristic that user accesses the network behavior of credit website
According to, and user accesses the network of Web bank or network payment website after credit website is accessed in the first preset time period
The characteristic of behavior;
According to the characteristic of the default user network behavior, judging user, whether there occurs net loan behavior.
Further, the default user network behavior also includes the network behavior that user searches for predetermined keyword;Institute
Stating the characteristic of default user network behavior also includes the characteristic that user searches for the network behavior of predetermined keyword.
Further, the characteristic of the network behavior of user's search predetermined keyword includes characteristic value including following
At least one of characteristic value:
Whether user occurs to search for the network behavior of predetermined keyword in the second preset time period;
User occurs to search for the number of the network behavior of predetermined keyword in the second preset time period;
User occurs to search for the maximum of the number of the network behavior of predetermined keyword within the unit interval.
Further, the characteristic of the network behavior of user's access credit website is included in following characteristics value extremely
Few one kind:
User averagely accesses the number of credit website daily;
User accesses the maximum of the number of credit website within the unit interval;
User accesses the maximum number of species of the credit website of different credit websites daily;
The access depth that user accesses the web page address of credit website in the 3rd preset time period is more than pre-set level
Number;
User accesses the number of credit website in the 3rd preset time period;
User accesses the number of species of the credit website of different credit websites in the 3rd preset time period.
Further, Web bank or network are accessed in the first preset time period behind user's access credit website
The characteristic of the network behavior of paying website includes characteristic value:User accesses the interior visit of the first preset time period behind credit website
Ask the number of the network behavior of Web bank or network payment website.
Further, the characteristic according to the default user network behavior, judge user whether there occurs
Also include step after the step of net loan behavior:When it is determined that net loan behavior occurs, cumulative calculation user in predetermined period sends out
The number of raw net loan behavior.
Further, the characteristic according to the default user network behavior, judge user whether there occurs
The step of net loan behavior, includes:
Judge that user is according to the characteristic of the default user network behavior, and default discrimination model algorithm
It is no that there occurs net loan behavior.
Further, the default discrimination model includes Logic Regression Models, the algorithm bag of the default discrimination model
Include
Wherein, the x is the characteristic value of the characteristic of the default user network behavior, and i is Logic Regression Models
Middle vectorThe 7th element.
The present invention also provides a kind of data processing equipment, including memory, processor and storage are on a memory and can be
The computer program run on processor, the step of above-mentioned data processing method is realized during the computing device described program
Suddenly.
The present invention also provides a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that should
The step of above-mentioned data processing method is realized when program is executed by processor.
In the present invention, by gather user access credit website network behavior and family after credit website is accessed it is pre-
If the network behavior of Web bank or network payment website, the two the default use related to net loan behavior are accessed in the time
The Internet data of family network behavior, the characteristic of default user network behavior is obtained, then according to the default user
The characteristic of network behavior, judge that user whether there occurs net loan behavior, has reached the net loan behavior that can be realized to user
The technique effect for being identified and monitoring.
Brief description of the drawings
Fig. 1 is the flow chart of the data processing method in first embodiment of the invention;
Fig. 2 is the flow chart of the data processing method in second embodiment of the invention;
Fig. 3 is the flow chart of the data processing method in third embodiment of the invention;
Fig. 4 is the table of the characteristic value of the characteristic of the default user network behavior in an embodiment of the present invention;
Fig. 5 is the flow chart of the data processing method in four embodiment of the invention;
Fig. 6 is the modular structure schematic diagram of the data processing equipment in an embodiment of the present invention.
The realization, functional characteristics and advantage of the object of the invention will be described further referring to the drawings in conjunction with the embodiments.
Embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
Fig. 1 is refer to, Fig. 1 is the data processing method 100 for being used to identify net loan behavior in first embodiment of the invention
Method flow diagram, wherein, the data processing method 100 comprises the following steps:
Step S10, gathers the Internet data of default user network behavior, and the default user network behavior includes using
Family accesses the network behavior of credit website, and user accesses Web bank or net after credit website is accessed in preset time
The network behavior of network paying website.
The net loan behavior of user is always closely bound up with some specific collectable network behaviors of user.Such as user
The network behavior of credit website is accessed, the network behavior can be detected with collecting by web browser, specifically, can be by setting
A credit list of websites is put, the historical record of the browser of user and credit list of websites are compared to obtain user's access
The Internet data of the network behavior of credit website, it is to be understood that those skilled in the art, which are known that, to be used specific collection
The mode that family accesses the Internet data of the network behavior of credit website has many kinds, will not be described here, does not also limit specifically
It is fixed.
In another example user accesses the network behavior of Web bank or network payment website, the network behavior can be in net
Go to bank or behavior that the network payment website/platform such as Alipay, wechat wallet is paid the bill;Can also be that user accesses net
Go to bank or the behavior of the network payment website/platform such as Alipay, wechat wallet.Specifically, the network behavior can pass through
The website of user's access or the domain name of network linking are analyzed to judge whether user have accessed Web bank, have payment function
The network behavior such as internet payment platform, the network behavior can also by analyze user browser historical record whether
The payment successful webpage record that payment transaction server end feedback be present is used as and judges user access Web bank or net
The foundation of the network behavior of network paying website, it is to be understood that those skilled in the art, which are known that, to be visited specific collection family
Asking the mode of the Internet data of the network behavior of Web bank or network payment website has many kinds, will not be described here,
Do not limit specifically.
Specifically, in step slo, gather the Internet data of default user network behavior, the default user network
Network behavior includes the network behavior that user accesses credit website, and user accesses net after credit website is accessed in preset time
Go to bank or the network behavior of network payment website.
Step S20, default user network is obtained according to the Internet data of the default user network behavior collected
The characteristic of network behavior, the characteristic of the default user network behavior include the network row that user accesses credit website
For characteristic, and user accesses Web bank or network payment website after credit website is accessed in preset time
The characteristic of network behavior.
Specifically, in step S20, obtained and used according to the Internet data of the default user network behavior collected
Family accesses the characteristic of the network behavior of credit website;And according to the upper of the default user network behavior collected
Network data obtains user accesses Web bank or network payment website after credit website is accessed network row in preset time
For characteristic.
Step S30, according to the characteristic of the default user network behavior, judge whether user borrows there occurs net and go
For.
Specifically, the characteristic of the default user network behavior includes the network behavior that user accesses credit website
Characteristic, and user accesses the net of Web bank or network payment website after credit website is accessed in preset time
The characteristic of network behavior, can determining user according to the characteristic of the default user network behavior, whether there occurs net loan
Behavior.For example, the characteristic that user accesses the network behavior of credit website is not sky, and user is after credit website is accessed
In the case that the characteristic of the network behavior of access Web bank or network payment website is not for sky in preset time, judge
It is that there occurs net loan behavior for user.In another example the characteristic of the network behavior of credit website can be accessed by user
Quantity, and user access the network behavior of Web bank or network payment website after credit website is accessed in preset time
The quantity of characteristic whether be more than preset value and judge that user is that there occurs net loan behavior.It is to be appreciated that this is default
The characteristic of user network behavior represents user whether there occurs the probability of net loan behavior, those skilled in the art and can know
Road may determine that whether user borrows there occurs net by the mode such as suitable preset rules, specific model or algorithm and go
Not add to repeat herein.
In the present embodiment, the data processing method 100 accesses the network behavior of credit website by gathering user
And family accesses the network behavior of Web bank or network payment website after credit website is accessed in preset time, the two
The Internet data of the default user network behavior related to net loan behavior, obtain the characteristic of default user network behavior
According to then according to the characteristic of the default user network behavior, judging user, whether there occurs net loan behavior.
It is the data processing method for being used to identify net loan behavior in second embodiment of the present invention please also refer to Fig. 2
102 method flow diagram.In this second embodiment, it is default can also to include user's search for the default user network behavior
The network behavior of keyword;The characteristic of the default user network behavior can also include user and search for predetermined keyword
Network behavior characteristic.The data processing method 102 includes step:
Step S12, gathers the Internet data of default user network behavior, and the default user network behavior includes using
Family accesses the network behavior of credit website, and user accesses Web bank or network branch after credit website is accessed in preset time
The network behavior of website is paid, and user searches for the network behavior of predetermined keyword;
Step S22, default user network row is obtained according to the Internet data of the default user network behavior collected
For characteristic, the characteristic of the default user network behavior includes the network behavior that user accesses credit website
Characteristic, user access the network behavior of Web bank or network payment website after credit website is accessed in preset time
Characteristic, and user search for predetermined keyword network behavior characteristic;
Step S32, according to the characteristic of the default user network behavior, judge whether user borrows there occurs net and go
For.
In the present embodiment, the default user network behavior can also include the net that user searches for predetermined keyword
Network behavior;The characteristic of the default user network behavior can also include the network behavior that user searches for predetermined keyword
Characteristic.Data processing method 102 further gathers the network that the user related to net loan behavior searches for predetermined keyword
The Internet data of behavior, and the characteristic that user searches for the network behavior of predetermined keyword is obtained, it is pre- with reference to user search
If whether the characteristic of the network behavior of keyword judges user there occurs net loan behavior, the net for further increasing user is borrowed
The accuracy rate of the identification of behavior.
Fig. 3 is please combined in the lump, is the data processing method for being used to identify net loan behavior in third embodiment of the present invention
103 method flow diagram, the data processing method 103 is on the basis of data processing method 100, in addition to step S40, true
During fixed generation net loan behavior, the number of net loan behavior occurs for cumulative calculation user in predetermined period.
Specifically, after judging user there occurs net loan behavior in the step S33 of data processing method 103, further tire out
Meter calculates the number for the network behavior for being judged as net loan behavior.Wherein, the predetermined period can be one week, two weeks, three days
Or one day, it can also be arranged as required to.
In the present embodiment, other the step of with data processing method 100 the step of it is identical, will not be repeated here.Can
With understanding, step S40 can also be arranged on data processing method 102, or the data of other embodiment of the present invention
In processing method.
Fig. 4 is please combined in the lump, for the spy of the characteristic of the default user network behavior in an embodiment of the present invention
The table of value indicative.It is understood that the characteristic value of the characteristic of each user network behavior in the table can individually make
With can also be used in any combination.
Web bank or network payment website are accessed in the first preset time period behind user's access credit website
The characteristic of network behavior can include characteristic value:
User accesses the interior net for accessing Web bank or network payment website of the first preset time period behind credit website
The number of network behavior.
Wherein, first preset time period can be 15 minutes, half an hour or one hour, can also be as needed
Set.
Specifically, this feature value is user access credit website after the first preset time period in access Web bank or
The number of the network behavior of network payment website, the calculating of the number can not repeat, for example, user accesses credit there occurs multiple
After the network behavior of website, there occurs the network behavior for accessing Web bank or network payment website, only calculate between the time
Gauge is from first after the network behavior of the access credit website for the network behavior for accessing Web bank or network payment website
The network behavior of Web bank or network payment website is accessed in preset time period.
Wherein, the characteristic of the network behavior of user's search predetermined keyword can include characteristic value:
Whether user occurs to search for the network behavior of predetermined keyword in the second preset time period, is for investigating user
The behavior of no search credit keyword;
User occurs to search for the number of the network behavior of predetermined keyword in the second preset time period, for investigating second
User searches for the frequency and/or number of the behavior of credit keyword in preset time period;
User occurs to search for the maximum of the number of the network behavior of predetermined keyword within the unit interval, for investigating list
User searches for the frequency of behavior and/or the maximum of number of credit keyword in the time of position.
Wherein, second preset time period can be one day, half a day or a couple of days, can also be arranged as required to.It is excellent
Selection of land, second preset time period can be the users in the preset time period before accessing credit website.
The characteristic that the user accesses the network behavior of credit website can include characteristic value:
The access depth that user accesses the web page address of credit website in the 3rd preset time period is more than pre-set level
Number, for investigating the frequency and/or number of the network behavior of user's in-depth interview credit website in the unit interval, and exclude
The interference of the factors such as advertisement, reduce erroneous judgement;
User accesses the number of credit website in the 3rd preset time period, for investigating user in the 3rd preset time period
Access the frequency and/or number of the network behavior of credit website;
User accesses the number of species of the credit website of different credit websites in the 3rd preset time period, for investigating
User accesses the species number of the credit website of different credit websites in unit interval;
Wherein, the 3rd preset time period is one week, two weeks, one day, half a day or one hour, can also be according to need
Set.Preferably, the 3rd preset time period can also be user before Web bank or network payment website is accessed
Preset time period in.
It is understood that the access that the user accesses the web page address of credit website in the 3rd preset time period is deep
Degree can be user in URL (Uniform Resource Locator, URL) address of the credit website
Structure category access level.
For example, the depth of the URL addresses is 4, including " root-channel directory-subchannel catalogue-date catalogue-interior
Hold catalogue ", when user has access to root, now access depth and could be arranged to " 1 ", user only enters credit website
Homepage, it may be possible to user is overdue to be hit or the reason for pop-up, and user is so as to having had access to the homepage of credit website;When user visits
When asking channel directory, now access depth and could be arranged to " 2 ", show that user is interested from the information to credit website, and
The further second-level directory that has been linked into for clicking credit Website page, it now can be determined that the user accesses credit
The access depth of the web page address of website is more than pre-set level.It is understood that the definition of the value for accessing depth can be with
Set according to the depth of URL addresses;The pre-set level can also be arranged as required to.
The characteristic that the user accesses the network behavior of credit website can also include characteristic value:
User averagely accesses the number of credit website daily, wherein it is possible to only calculate the day that user have accessed credit website
Number;
User accesses the maximum of the number of credit website within the unit interval;
User accesses the maximum number of species of the credit website of different credit websites daily.
Fig. 5 is please combined in the lump, further, for the data processing method 104 in four embodiment of the invention, the data
Processing method 104 includes:
Step S10, gathers the Internet data of default user network behavior, and the default user network behavior includes using
Family accesses the network behavior of credit website, and user accesses Web bank or net after credit website is accessed in preset time
The network behavior of network paying website.
Step S20, default user network is obtained according to the Internet data of the default user network behavior collected
The characteristic of network behavior, the characteristic of the default user network behavior include the network row that user accesses credit website
For characteristic, and user accesses Web bank or network payment website after credit website is accessed in preset time
The characteristic of network behavior.
Step S33, sentenced according to the characteristic of the default user network behavior, and default discrimination model algorithm
Whether there occurs net loan behavior by disconnected user.
In the present embodiment, step S10 is identical with data processing method 100 with step S20, will not be repeated here.
Specifically, in step S33, can by presetting a discrimination model, come auxiliary judgment user whether there occurs
Net loan behavior.Wherein, the discrimination model can use the model of suitable influence factor and prediction of result, be instructed by model
Practice, the algorithmic formula of model prediction can be obtained.
In the present embodiment, the net that user can be further improved by using suitable discrimination model algorithm borrows row
For identification accuracy rate.
Further, in an embodiment of the present invention, the default discrimination model algorithm includes Logic Regression Models
(Logistic Regression models, LR models), the default discrimination model algorithm include
Wherein, the x is the characteristic value of the characteristic of the default user network behavior;I represents intercept,
It is vectorial specially in Logic Regression ModelsThe 7th element.
In the present embodiment, LR models are chosen as discrimination model algorithm, its can provide a sample whether be just/
The probability of negative sample, and this probability can be used as net to borrow value-at-risk output, so as to be ranked to risk subscribers;Pass through model
Training, finally draw the algorithmic formula of model prediction:
In True Data, the characteristic value of the characteristic by extracting default user network behavior, and application is above-mentioned
The algorithmic formula of LR models calculates, and the data processing method in present embodiment can identify that net of the accuracy rate more than 90% is borrowed
Behavior.
Fig. 6 is please combined in the lump, is the modular structure schematic diagram of the data processing equipment 200 in an embodiment of the present invention.
The data processing equipment 200 includes memory 201, processor 202 and storage on a memory and can handled
The computer program run on device 202, the processor 202 realize the steps when performing described program:
Step S10, gathers the Internet data of default user network behavior, and the default user network behavior includes using
Family accesses the network behavior of credit website, and user accesses Web bank or net after credit website is accessed in preset time
The network behavior of network paying website.
Step S20, default user network is obtained according to the Internet data of the default user network behavior collected
The characteristic of network behavior, the characteristic of the default user network behavior include the network row that user accesses credit website
For characteristic, and user accesses Web bank or network payment website after credit website is accessed in preset time
The characteristic of network behavior.
Step S30, according to the characteristic of the default user network behavior, judge whether user borrows there occurs net and go
For.
Wherein, the data processing equipment 200 can be the tool such as computer, portable computer device, mobile phone, tablet personal computer
The consumption electronic product of standby data processing function.By software corresponding to the installation on this kind of consumption electronic product, to user's
Internet data is analyzed caused by network behavior, is identified and is monitored so as to borrow behavior to the net of user so that guardian
Or whether the father and mother of student can be known using the consumption electronic product such as computer, tablet personal computer, mobile phone terminal people in P2P nets
Borrow on platform there occurs net loan behavior, do not possess loan qualification or insolvency loan with preventing such to prevent in time
Borrower carries out net loan.
The data processing equipment 200 can also be the network equipments such as gateway, server, by passing through on network devices
Software corresponding to installation, Internet data caused by the network behavior of user is analyzed, entered so as to borrow behavior to the net of user
Go and identify and monitor, the offer of the network equipment or manager, the mechanism of offer net loan platform or third-party monitoring person etc. have need to
The people wanted either tissue can detect and know such do not possess loan qualification or insolvency loan borrower carry out net
The behavior of loan.
In one embodiment, the step S30 can be specially:According to the feature of the default user network behavior
Data, and default discrimination model algorithm judge user whether there occurs net loan behavior.
In one embodiment, the steps can also be realized when the processor 202 performs described program:
Step S12, gathers the Internet data of default user network behavior, and the default user network behavior includes using
Family accesses the network behavior of credit website, and user accesses Web bank or network branch after credit website is accessed in preset time
The network behavior of website is paid, and user searches for the network behavior of predetermined keyword;
Step S22, default user network row is obtained according to the Internet data of the default user network behavior collected
For characteristic, the characteristic of the default user network behavior includes the network behavior that user accesses credit website
Characteristic, user access the network behavior of Web bank or network payment website after credit website is accessed in preset time
Characteristic, and user search for predetermined keyword network behavior characteristic;
Step S32, according to the characteristic of the default user network behavior, judge whether user borrows there occurs net and go
For.
In one embodiment, the step S32 can be specially:According to the feature of the default user network behavior
Data, and default discrimination model algorithm judge user whether there occurs net loan behavior.
In one embodiment, step can also be realized when the processor 202 performs described program:It is determined that net occurs
During loan behavior, the number of net loan behavior occurs for cumulative calculation user in predetermined period.Wherein, the predetermined period can be one
In week, two weeks, three days or one day, it can also be arranged as required to.
Wherein, Web bank or network payment are accessed in the first preset time period behind user's access credit website
The characteristic of the network behavior of website can include characteristic value:
User accesses the interior net for accessing Web bank or network payment website of the first preset time period behind credit website
The number of network behavior.Wherein, first preset time period can be 15 minutes, half an hour or one hour, can also root
According to needing to set.
Specifically, this feature value is user access credit website after the first preset time period in access Web bank or
The number of the network behavior of network payment website, the calculating of the number can not repeat, for example, user accesses credit there occurs multiple
After the network behavior of website, there occurs the network behavior for accessing Web bank or network payment website, only calculate between the time
Gauge is from first after the network behavior of the access credit website for the network behavior for accessing Web bank or network payment website
The network behavior of Web bank or network payment website is accessed in preset time period.
The characteristic that the user searches for the network behavior of predetermined keyword can include characteristic value:
Whether user occurs to search for the network behavior of predetermined keyword in the second preset time period, is for investigating user
The behavior of no search credit keyword;
User occurs to search for the number of the network behavior of predetermined keyword in the second preset time period, for investigating second
User searches for the frequency and/or number of the behavior of credit keyword in preset time period;
User occurs to search for the maximum of the number of the network behavior of predetermined keyword within the unit interval, for investigating list
User searches for the frequency of behavior and/or the maximum of number of credit keyword in the time of position.
Wherein, second preset time period can be one day, half a day or a couple of days, can also be arranged as required to.It is excellent
Selection of land, second preset time period can be the users in the preset time period before accessing credit website.
The characteristic that the user accesses the network behavior of credit website can include characteristic value:
The access depth that user accesses the web page address of credit website in the 3rd preset time period is more than pre-set level
Number, for investigating the frequency and/or number of the network behavior of user's in-depth interview credit website in the unit interval, and exclude
The interference of the factors such as advertisement, reduce erroneous judgement;
User accesses the number of credit website in the 3rd preset time period, for investigating user in the 3rd preset time period
Access the frequency and/or number of the network behavior of credit website;
User accesses the number of species of the credit website of different credit websites in the 3rd preset time period, for investigating
User accesses the species number of the credit website of different credit websites in unit interval;
Wherein, the 3rd preset time period is one week, two weeks, one day, half a day or one hour, can also be according to need
Set.Preferably, the 3rd preset time period can also be user before Web bank or network payment website is accessed
Preset time period in.
The characteristic that the user accesses the network behavior of credit website can also include characteristic value:
User averagely accesses the number of credit website daily, wherein it is possible to only calculate the day that user have accessed credit website
Number;
User accesses the maximum of the number of credit website within the unit interval;
User accesses the maximum number of species of the credit website of different credit websites daily.
It is understood that the characteristic value of the characteristic of each user network behavior in the table can individually make
With can also be used in any combination.
The data processing equipment 200 provided in the present invention, the network behavior of credit website can be accessed by gathering user
And family accesses the network behavior of Web bank or network payment website after credit website is accessed in preset time, the two
The Internet data of the default user network behavior related to net loan behavior, obtain the characteristic of default user network behavior
According to then according to the characteristic of the default user network behavior, judging user, whether there occurs net loan behavior.Reach
It can realize that borrowing behavior to the net of user is identified on the data processing equipments such as computer, mobile phone terminal, the network equipment 200
With the technique effect of monitoring, and then the father and mother of guardian or student are allowd to know the people using the related electronic installation
Whether net and borrowed on platform there occurs net loan behavior in P2P, do not possess loan qualification or nothing with preventing such to prevent in time
The borrower that power is repaid the loan carries out net loan.
The present invention also provides a kind of computer-readable recording medium, is stored thereon with computer program, the program is processed
Device can realize data processing method 100 as described above, data processing method 102, data processing method 103, number when performing
The step of according to processing method 104.
It is understood that in the description of this specification, reference term " embodiment ", " another embodiment ", " other
The description of embodiment " or " first embodiment~N embodiments " etc. means to combine the specific spy that the embodiment or example describe
Sign, structure, material or feature are contained at least one embodiment or example of the present invention.In this manual, to above-mentioned
The schematic representation of term is not necessarily referring to identical embodiment or example.Moreover, the specific features of description, structure, material
Or feature can combine in an appropriate manner in any one or more embodiments or example.
It should be noted that herein, term " comprising ", "comprising" or its any other variant are intended to non-row
His property includes, so that process, method, article or system including a series of elements not only include those key elements, and
And also include the other element being not expressly set out, or also include for this process, method, article or system institute inherently
Key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that including this
Other identical element also be present in the process of key element, method, article or system.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on such understanding, technical scheme is substantially done to prior art in other words
Going out the part of contribution can be embodied in the form of software product, and the computer software product is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disc, CD), including some instructions to cause a station terminal equipment (can be mobile phone,
Computer, server, air conditioner, or network equipment etc.) perform method described in each embodiment of the present invention.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
It is understood that these are only the preferred embodiments of the present invention, it is not intended to limit the scope of the invention,
Every equivalent structure made using description of the invention and accompanying drawing content or equivalent flow conversion, or be directly or indirectly used in
Other related technical areas, it is included within the scope of the present invention.
Claims (10)
1. a kind of data processing method for being used to identify net loan behavior, it is characterised in that comprise the following steps:
The Internet data of default user network behavior is gathered, the default user network behavior includes user and accesses credit net
The network behavior stood, and user access Web bank or network payment website after credit website is accessed in preset time
Network behavior;
The characteristic of default user network behavior is obtained according to the Internet data of the default user network behavior collected,
The characteristic of the default user network behavior includes the characteristic that user accesses the network behavior of credit website, and
User accesses the network behavior of Web bank or network payment website after credit website is accessed in the first preset time period
Characteristic;
According to the characteristic of the default user network behavior, judging user, whether there occurs net loan behavior.
2. data processing method as claimed in claim 1, it is characterised in that the default user network behavior also includes using
The network behavior of predetermined keyword is searched at family;It is default that the characteristic of the default user network behavior also includes user's search
The characteristic of the network behavior of keyword.
3. data processing method as claimed in claim 2, it is characterised in that the user searches for the network row of predetermined keyword
For characteristic include at least one of following characteristics value:
Whether user occurs to search for the network behavior of predetermined keyword in the second preset time period;
User occurs to search for the number of the network behavior of predetermined keyword in the second preset time period;
User occurs to search for the maximum of the number of the network behavior of predetermined keyword within the unit interval.
4. data processing method as claimed in claim 1, it is characterised in that the user accesses the network behavior of credit website
Characteristic include at least one of following characteristics value:
User averagely accesses the number of credit website daily;
User accesses the maximum of the number of credit website within the unit interval;
User accesses the maximum number of species of the credit website of different credit websites daily;
User accesses number of the access depth more than pre-set level of the web page address of credit website in the 3rd preset time period;
User accesses the number of credit website in the 3rd preset time period;
User accesses the number of species of the credit website of different credit websites in the 3rd preset time period.
5. data processing method as claimed in claim 1, it is characterised in that first behind user's access credit website is pre-
Include characteristic value if accessing the characteristic of the network behavior of Web bank or network payment website in the period:User accesses
The number of the network behavior of Web bank or network payment website is accessed in the first preset time period behind credit website.
6. data processing method as claimed in claim 1, it is characterised in that described according to the default user network behavior
Characteristic, judging user, whether there occurs also include step after the step of net loan behavior:It is determined that net loan behavior occurs
When, the number of net loan behavior occurs for cumulative calculation user in predetermined period.
7. the data processing method as described in claim 1~6, it is characterised in that described according to the default user network
The characteristic of behavior, judge user whether there occurs the step of net loan behavior to include:
Judge whether user sends out according to the characteristic of the default user network behavior, and default discrimination model algorithm
Net loan behavior is given birth to.
8. data processing method as claimed in claim 7, it is characterised in that the default discrimination model includes logistic regression
Model, the algorithm of the default discrimination model include
<mrow>
<mover>
<mi>&theta;</mi>
<mo>&RightArrow;</mo>
</mover>
<mo>&CenterDot;</mo>
<mover>
<mi>x</mi>
<mo>&RightArrow;</mo>
</mover>
<mo>=</mo>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
<msub>
<mi>&theta;</mi>
<mn>1</mn>
</msub>
<mo>+</mo>
<msub>
<mi>x</mi>
<mn>2</mn>
</msub>
<msub>
<mi>&theta;</mi>
<mn>2</mn>
</msub>
<mo>+</mo>
<mo>...</mo>
<mo>+</mo>
<msub>
<mi>x</mi>
<mn>6</mn>
</msub>
<msub>
<mi>&theta;</mi>
<mn>6</mn>
</msub>
<mo>+</mo>
<mi>i</mi>
<mo>;</mo>
</mrow>
Wherein, the x be the default user network behavior characteristic characteristic value, i be Logic Regression Models in
AmountThe 7th element.
9. a kind of data processing equipment, including memory, processor and storage can be run on a memory and on a processor
Computer program, it is characterised in that realized during the computing device described program as any one of claim 1 to 8
Data processing method the step of.
10. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is by processor
The step of data processing method as any one of claim 1 to 8 is realized during execution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710701240.8A CN107622443B (en) | 2017-08-16 | 2017-08-16 | Data processing method, data processing apparatus, and computer-readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710701240.8A CN107622443B (en) | 2017-08-16 | 2017-08-16 | Data processing method, data processing apparatus, and computer-readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107622443A true CN107622443A (en) | 2018-01-23 |
CN107622443B CN107622443B (en) | 2021-09-17 |
Family
ID=61088768
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710701240.8A Active CN107622443B (en) | 2017-08-16 | 2017-08-16 | Data processing method, data processing apparatus, and computer-readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107622443B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109933744A (en) * | 2018-08-10 | 2019-06-25 | 深信服科技股份有限公司 | Target identification method and device, equipment and computer readable storage medium |
CN110929525A (en) * | 2019-10-23 | 2020-03-27 | 三明学院 | Network loan risk behavior analysis and detection method, device, equipment and storage medium |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106330837A (en) * | 2015-06-30 | 2017-01-11 | 阿里巴巴集团控股有限公司 | Suspicious network user identification method and device |
-
2017
- 2017-08-16 CN CN201710701240.8A patent/CN107622443B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106330837A (en) * | 2015-06-30 | 2017-01-11 | 阿里巴巴集团控股有限公司 | Suspicious network user identification method and device |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109933744A (en) * | 2018-08-10 | 2019-06-25 | 深信服科技股份有限公司 | Target identification method and device, equipment and computer readable storage medium |
CN110929525A (en) * | 2019-10-23 | 2020-03-27 | 三明学院 | Network loan risk behavior analysis and detection method, device, equipment and storage medium |
CN110929525B (en) * | 2019-10-23 | 2022-08-05 | 三明学院 | Network loan risk behavior analysis and detection method, device, equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN107622443B (en) | 2021-09-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20210166140A1 (en) | Method and apparatus for training risk identification model and server | |
Peng et al. | Modeling and predicting extreme cyber attack rates via marked point processes | |
US8620746B2 (en) | Scoring quality of traffic to network sites | |
Martin et al. | Why experience matters to privacy: How context‐based experience moderates consumer privacy expectations for mobile applications | |
US20130339350A1 (en) | Ranking Search Results Based on Click Through Rates | |
CN104281718B (en) | A kind of method that intelligent recommendation is excavated based on user group's behavioral data | |
US20090327120A1 (en) | Tagged Credit Profile System for Credit Applicants | |
CN105469263A (en) | Commodity recommendation method and device | |
CN106897334A (en) | A kind of question pushing method and equipment | |
CN106022800A (en) | User feature data processing method and device | |
CA2905280A1 (en) | Automated financial data aggregation | |
CN110689438A (en) | Enterprise financial risk scoring method and device, computer equipment and storage medium | |
CN107798607A (en) | Asset Allocation strategy acquisition methods, device, computer equipment and storage medium | |
CN103797477A (en) | Predicting user navigation events | |
CN103605714B (en) | The recognition methods of website abnormal data and device | |
US20150287051A1 (en) | System and method for identifying growing companies and monitoring growth using non-obvious parameters | |
US20060224499A1 (en) | Method and apparatus for computing a loan quality score | |
CN106528777A (en) | Cross-screen user identification normalizing method and system | |
CN103593446A (en) | Flow quality analyzing method and device | |
CN110413635A (en) | A kind of data processing method and device | |
CN107622443A (en) | Data processing method, data processing equipment and computer-readable recording medium | |
Ramakrishna et al. | Web mining: Key accomplishments, applications and future directions | |
CN111061948A (en) | User label recommendation method and device, computer equipment and storage medium | |
CN111967802A (en) | Enterprise financial risk quantitative analysis and early warning method, device and equipment | |
CN107135199A (en) | The detection method and device at webpage back door |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |